Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 191 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.3347. Min Act: -0.0001

Data Index: 465242 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.3305. Min Act: -0.0001

Data Index: 71005 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.3183. Min Act: -0.0001

Data Index: 175812 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.3142. Min Act: -0.0001

Data Index: 1092205 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2890. Min Act: -0.0001

Data Index: 454096 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.3084. Min Act: -0.0001

Data Index: 1153388 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.3249. Min Act: -0.0001

Data Index: 281241 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2924. Min Act: -0.0001

Data Index: 916567 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2835. Min Act: -0.0001

Data Index: 898861 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2916. Min Act: -0.0001

Data Index: 433166 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2921. Min Act: -0.0001

Data Index: 517052 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.3050. Min Act: -0.0001

Data Index: 26098 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2856. Min Act: -0.0001

Data Index: 1157536 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2702. Min Act: -0.0001

Data Index: 1203265 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2674. Min Act: -0.0001

Data Index: 253514 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2831. Min Act: -0.0001

Data Index: 682611 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2646. Min Act: -0.0001

Data Index: 8518 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2755. Min Act: -0.0001

Data Index: 607739 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2682. Min Act: -0.0001

Data Index: 262306 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2752. Min Act: -0.0001

Data Index: 515520 (C4 (Web Text))

Max Activating Token Index: 77